16 files changed, 162 insertions, 36 deletions

diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index 6def0351bcc3..14b789a123e7 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -265,6 +265,11 @@ extern const struct ipv6_stub *ipv6_stub __read_mostly;
 struct ipv6_bpf_stub {
 	int (*inet6_bind)(struct sock *sk, struct sockaddr *uaddr, int addr_len,
 			  bool force_bind_address_no_port, bool with_lock);
+	struct sock *(*udp6_lib_lookup)(struct net *net,
+					const struct in6_addr *saddr, __be16 sport,
+					const struct in6_addr *daddr, __be16 dport,
+					int dif, int sdif, struct udp_table *tbl,
+					struct sk_buff *skb);
 };
 extern const struct ipv6_bpf_stub *ipv6_bpf_stub __read_mostly;
 
diff --git a/include/net/dst.h b/include/net/dst.h
index 7f735e76ca73..6cf0870414c7 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -527,4 +527,14 @@ static inline void skb_dst_update_pmtu(struct sk_buff *skb, u32 mtu)
 		dst->ops->update_pmtu(dst, NULL, skb, mtu);
 }
 
+static inline void skb_tunnel_check_pmtu(struct sk_buff *skb,
+					 struct dst_entry *encap_dst,
+					 int headroom)
+{
+	u32 encap_mtu = dst_mtu(encap_dst);
+
+	if (skb->len > encap_mtu - headroom)
+		skb_dst_update_pmtu(skb, encap_mtu - headroom);
+}
+
 #endif /* _NET_DST_H */
diff --git a/include/net/inet_ecn.h b/include/net/inet_ecn.h
index 482a1b705362..c8e2bebd8d93 100644
--- a/include/net/inet_ecn.h
+++ b/include/net/inet_ecn.h
@@ -183,8 +183,7 @@ static inline int INET_ECN_set_ce(struct sk_buff *skb)
  *          1 if something is broken and should be logged (!!! above)
  *          2 if packet should be dropped
  */
-static inline int INET_ECN_decapsulate(struct sk_buff *skb,
-				       __u8 outer, __u8 inner)
+static inline int __INET_ECN_decapsulate(__u8 outer, __u8 inner, bool *set_ce)
 {
 	if (INET_ECN_is_not_ect(inner)) {
 		switch (outer & INET_ECN_MASK) {
@@ -198,10 +197,21 @@ static inline int INET_ECN_decapsulate(struct sk_buff *skb,
 		}
 	}
 
-	if (INET_ECN_is_ce(outer))
+	*set_ce = INET_ECN_is_ce(outer);
+	return 0;
+}
+
+static inline int INET_ECN_decapsulate(struct sk_buff *skb,
+				       __u8 outer, __u8 inner)
+{
+	bool set_ce = false;
+	int rc;
+
+	rc = __INET_ECN_decapsulate(outer, inner, &set_ce);
+	if (!rc && set_ce)
 		INET_ECN_set_ce(skb);
 
-	return 0;
+	return rc;
 }
 
 static inline int IP_ECN_decapsulate(const struct iphdr *oiph,
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index caabfd84a098..84097010237c 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -159,6 +159,10 @@ struct fib6_info {
 	struct rt6_info * __percpu	*rt6i_pcpu;
 	struct rt6_exception_bucket __rcu *rt6i_exception_bucket;
 
+#ifdef CONFIG_IPV6_ROUTER_PREF
+	unsigned long			last_probe;
+#endif
+
 	u32				fib6_metric;
 	u8				fib6_protocol;
 	u8				fib6_type;
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index cef186dbd2ce..7ab119936e69 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -174,6 +174,7 @@ struct rt6_rtnl_dump_arg {
 	struct sk_buff *skb;
 	struct netlink_callback *cb;
 	struct net *net;
+	struct fib_dump_filter filter;
 };
 
 int rt6_dump_route(struct fib6_info *f6i, void *p_arg);
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 852e4ebf2209..e8d9456bf36e 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -222,6 +222,16 @@ struct fib_table {
 	unsigned long		__data[0];
 };
 
+struct fib_dump_filter {
+	u32			table_id;
+	/* filter_set is an optimization that an entry is set */
+	bool			filter_set;
+	unsigned char		protocol;
+	unsigned char		rt_type;
+	unsigned int		flags;
+	struct net_device	*dev;
+};
+
 int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp,
 		     struct fib_result *res, int fib_flags);
 int fib_table_insert(struct net *, struct fib_table *, struct fib_config *,
@@ -229,7 +239,7 @@ int fib_table_insert(struct net *, struct fib_table *, struct fib_config *,
 int fib_table_delete(struct net *, struct fib_table *, struct fib_config *,
 		     struct netlink_ext_ack *extack);
 int fib_table_dump(struct fib_table *table, struct sk_buff *skb,
-		   struct netlink_callback *cb);
+		   struct netlink_callback *cb, struct fib_dump_filter *filter);
 int fib_table_flush(struct net *net, struct fib_table *table);
 struct fib_table *fib_trie_unmerge(struct fib_table *main_tb);
 void fib_table_flush_external(struct fib_table *table);
@@ -453,6 +463,7 @@ static inline void fib_proc_exit(struct net *net)
 
 u32 ip_mtu_from_fib_result(struct fib_result *res, __be32 daddr);
 
-int ip_valid_fib_dump_req(const struct nlmsghdr *nlh,
-			  struct netlink_ext_ack *extack);
+int ip_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh,
+			  struct fib_dump_filter *filter,
+			  struct netlink_callback *cb);
 #endif  /* _NET_FIB_H */
diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h
index 0e355f4a3d76..77e2761d4f2f 100644
--- a/include/net/netfilter/nf_flow_table.h
+++ b/include/net/netfilter/nf_flow_table.h
@@ -99,7 +99,7 @@ int nf_flow_table_iterate(struct nf_flowtable *flow_table,
 			  void (*iter)(struct flow_offload *flow, void *data),
 			  void *data);
 
-void nf_flow_table_cleanup(struct net *net, struct net_device *dev);
+void nf_flow_table_cleanup(struct net_device *dev);
 
 int nf_flow_table_init(struct nf_flowtable *flow_table);
 void nf_flow_table_free(struct nf_flowtable *flow_table);
diff --git a/include/net/netfilter/nfnetlink_log.h b/include/net/netfilter/nfnetlink_log.h
deleted file mode 100644
index ea32a7d3cf1b..000000000000
--- a/include/net/netfilter/nfnetlink_log.h
+++ /dev/null
@@ -1 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
diff --git a/include/net/sctp/constants.h b/include/net/sctp/constants.h
index 86f034b524d4..8dadc74c22e7 100644
--- a/include/net/sctp/constants.h
+++ b/include/net/sctp/constants.h
@@ -148,11 +148,6 @@ SCTP_SUBTYPE_CONSTRUCTOR(PRIMITIVE,	enum sctp_event_primitive, primitive)
 #define sctp_chunk_is_data(a) (a->chunk_hdr->type == SCTP_CID_DATA || \
 			       a->chunk_hdr->type == SCTP_CID_I_DATA)
 
-/* Calculate the actual data size in a data chunk */
-#define SCTP_DATA_SNDSIZE(c) ((int)((unsigned long)(c->chunk_end) - \
-				    (unsigned long)(c->chunk_hdr) - \
-				    sctp_datachk_len(&c->asoc->stream)))
-
 /* Internal error codes */
 enum sctp_ierror {
 	SCTP_IERROR_NO_ERROR	        = 0,
diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h
index 5ef1bad81ef5..9e3d32746430 100644
--- a/include/net/sctp/sm.h
+++ b/include/net/sctp/sm.h
@@ -347,7 +347,7 @@ static inline __u16 sctp_data_size(struct sctp_chunk *chunk)
 	__u16 size;
 
 	size = ntohs(chunk->chunk_hdr->length);
-	size -= sctp_datahdr_len(&chunk->asoc->stream);
+	size -= sctp_datachk_len(&chunk->asoc->stream);
 
 	return size;
 }
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 28a7c8e44636..a11f93790476 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -876,6 +876,8 @@ struct sctp_transport {
 	unsigned long sackdelay;
 	__u32 sackfreq;
 
+	atomic_t mtu_info;
+
 	/* When was the last time that we heard from this transport? We use
 	 * this to pick new active and retran paths.
 	 */
diff --git a/include/net/sock.h b/include/net/sock.h
index 751549ac0a84..2440f8b407eb 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -422,8 +422,8 @@ struct sock {
 	struct timer_list	sk_timer;
 	__u32			sk_priority;
 	__u32			sk_mark;
-	u32			sk_pacing_rate; /* bytes per second */
-	u32			sk_max_pacing_rate;
+	unsigned long		sk_pacing_rate; /* bytes per second */
+	unsigned long		sk_max_pacing_rate;
 	struct page_frag	sk_frag;
 	netdev_features_t	sk_route_caps;
 	netdev_features_t	sk_route_nocaps;
@@ -2214,10 +2214,6 @@ static inline struct page_frag *sk_page_frag(struct sock *sk)
 
 bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag);
 
-int sk_alloc_sg(struct sock *sk, int len, struct scatterlist *sg,
-		int sg_start, int *sg_curr, unsigned int *sg_size,
-		int first_coalesce);
-
 /*
  *	Default write policy as shown to user space via poll/select/SIGIO
  */
diff --git a/include/net/switchdev.h b/include/net/switchdev.h
index d574ce63bf22..881ecb1555bf 100644
--- a/include/net/switchdev.h
+++ b/include/net/switchdev.h
@@ -145,6 +145,10 @@ enum switchdev_notifier_type {
 	SWITCHDEV_FDB_ADD_TO_DEVICE,
 	SWITCHDEV_FDB_DEL_TO_DEVICE,
 	SWITCHDEV_FDB_OFFLOADED,
+
+	SWITCHDEV_VXLAN_FDB_ADD_TO_DEVICE,
+	SWITCHDEV_VXLAN_FDB_DEL_TO_DEVICE,
+	SWITCHDEV_VXLAN_FDB_OFFLOADED,
 };
 
 struct switchdev_notifier_info {
@@ -155,7 +159,8 @@ struct switchdev_notifier_fdb_info {
 	struct switchdev_notifier_info info; /* must be first */
 	const unsigned char *addr;
 	u16 vid;
-	bool added_by_user;
+	u8 added_by_user:1,
+	   offloaded:1;
 };
 
 static inline struct net_device *
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 0d2929223c70..3600ae0f25c3 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -858,6 +858,21 @@ static inline void bpf_compute_data_end_sk_skb(struct sk_buff *skb)
 	TCP_SKB_CB(skb)->bpf.data_end = skb->data + skb_headlen(skb);
 }
 
+static inline bool tcp_skb_bpf_ingress(const struct sk_buff *skb)
+{
+	return TCP_SKB_CB(skb)->bpf.flags & BPF_F_INGRESS;
+}
+
+static inline struct sock *tcp_skb_bpf_redirect_fetch(struct sk_buff *skb)
+{
+	return TCP_SKB_CB(skb)->bpf.sk_redir;
+}
+
+static inline void tcp_skb_bpf_redirect_clear(struct sk_buff *skb)
+{
+	TCP_SKB_CB(skb)->bpf.sk_redir = NULL;
+}
+
 #if IS_ENABLED(CONFIG_IPV6)
 /* This is the variant of inet6_iif() that must be used by TCP,
  * as TCP moves IP6CB into a different location in skb->cb[]
@@ -2057,7 +2072,6 @@ struct tcp_ulp_ops {
 int tcp_register_ulp(struct tcp_ulp_ops *type);
 void tcp_unregister_ulp(struct tcp_ulp_ops *type);
 int tcp_set_ulp(struct sock *sk, const char *name);
-int tcp_set_ulp_id(struct sock *sk, const int ulp);
 void tcp_get_available_ulp(char *buf, size_t len);
 void tcp_cleanup_ulp(struct sock *sk);
 
@@ -2065,6 +2079,18 @@ void tcp_cleanup_ulp(struct sock *sk);
 	__MODULE_INFO(alias, alias_userspace, name);		\
 	__MODULE_INFO(alias, alias_tcp_ulp, "tcp-ulp-" name)
 
+struct sk_msg;
+struct sk_psock;
+
+int tcp_bpf_init(struct sock *sk);
+void tcp_bpf_reinit(struct sock *sk);
+int tcp_bpf_sendmsg_redir(struct sock *sk, struct sk_msg *msg, u32 bytes,
+			  int flags);
+int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
+		    int nonblock, int flags, int *addr_len);
+int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock,
+		      struct msghdr *msg, int len);
+
 /* Call BPF_SOCK_OPS program that returns an int. If the return value
  * is < 0, then the BPF op failed (for example if the loaded BPF
  * program does not support the chosen operation or there is no BPF
diff --git a/include/net/tls.h b/include/net/tls.h
index 5e853835597e..bab5627ff5e3 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -39,6 +39,8 @@
 #include <linux/crypto.h>
 #include <linux/socket.h>
 #include <linux/tcp.h>
+#include <linux/skmsg.h>
+
 #include <net/tcp.h>
 #include <net/strparser.h>
 #include <crypto/aead.h>
@@ -103,15 +105,13 @@ struct tls_rec {
 	int tx_flags;
 	int inplace_crypto;
 
-	/* AAD | sg_plaintext_data | sg_tag */
-	struct scatterlist sg_plaintext_data[MAX_SKB_FRAGS + 1];
-	/* AAD | sg_encrypted_data (data contain overhead for hdr&iv&tag) */
-	struct scatterlist sg_encrypted_data[MAX_SKB_FRAGS + 1];
+	struct sk_msg msg_plaintext;
+	struct sk_msg msg_encrypted;
 
-	unsigned int sg_plaintext_size;
-	unsigned int sg_encrypted_size;
-	int sg_plaintext_num_elem;
-	int sg_encrypted_num_elem;
+	/* AAD | msg_plaintext.sg.data | sg_tag */
+	struct scatterlist sg_aead_in[2];
+	/* AAD | msg_encrypted.sg.data (data contains overhead for hdr & iv & tag) */
+	struct scatterlist sg_aead_out[2];
 
 	char aad_space[TLS_AAD_SPACE_SIZE];
 	struct aead_request aead_req;
@@ -142,8 +142,7 @@ struct tls_sw_context_rx {
 
 	struct strparser strp;
 	void (*saved_data_ready)(struct sock *sk);
-	unsigned int (*sk_poll)(struct file *file, struct socket *sock,
-				struct poll_table_struct *wait);
+
 	struct sk_buff *recv_pkt;
 	u8 control;
 	bool decrypted;
@@ -223,8 +222,8 @@ struct tls_context {
 
 	unsigned long flags;
 	bool in_tcp_sendpages;
+	bool pending_open_record_frags;
 
-	u16 pending_open_record_frags;
 	int (*push_pending_record)(struct sock *sk, int flags);
 
 	void (*sk_write_space)(struct sock *sk);
@@ -272,8 +271,7 @@ void tls_sw_free_resources_rx(struct sock *sk);
 void tls_sw_release_resources_rx(struct sock *sk);
 int tls_sw_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		   int nonblock, int flags, int *addr_len);
-unsigned int tls_sw_poll(struct file *file, struct socket *sock,
-			 struct poll_table_struct *wait);
+bool tls_sw_stream_read(const struct sock *sk);
 ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos,
 			   struct pipe_inode_info *pipe,
 			   size_t len, unsigned int flags);
diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index 7ef15179f263..03431c148e16 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -5,6 +5,8 @@
 #include <linux/if_vlan.h>
 #include <net/udp_tunnel.h>
 #include <net/dst_metadata.h>
+#include <net/rtnetlink.h>
+#include <net/switchdev.h>
 
 /* VXLAN protocol (RFC 7348) header:
  * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
@@ -190,6 +192,7 @@ union vxlan_addr {
 struct vxlan_rdst {
 	union vxlan_addr	 remote_ip;
 	__be16			 remote_port;
+	u8			 offloaded:1;
 	__be32			 remote_vni;
 	u32			 remote_ifindex;
 	struct list_head	 list;
@@ -370,4 +373,65 @@ static inline unsigned short vxlan_get_sk_family(struct vxlan_sock *vs)
 	return vs->sock->sk->sk_family;
 }
 
+#if IS_ENABLED(CONFIG_IPV6)
+
+static inline bool vxlan_addr_any(const union vxlan_addr *ipa)
+{
+	if (ipa->sa.sa_family == AF_INET6)
+		return ipv6_addr_any(&ipa->sin6.sin6_addr);
+	else
+		return ipa->sin.sin_addr.s_addr == htonl(INADDR_ANY);
+}
+
+static inline bool vxlan_addr_multicast(const union vxlan_addr *ipa)
+{
+	if (ipa->sa.sa_family == AF_INET6)
+		return ipv6_addr_is_multicast(&ipa->sin6.sin6_addr);
+	else
+		return IN_MULTICAST(ntohl(ipa->sin.sin_addr.s_addr));
+}
+
+#else /* !IS_ENABLED(CONFIG_IPV6) */
+
+static inline bool vxlan_addr_any(const union vxlan_addr *ipa)
+{
+	return ipa->sin.sin_addr.s_addr == htonl(INADDR_ANY);
+}
+
+static inline bool vxlan_addr_multicast(const union vxlan_addr *ipa)
+{
+	return IN_MULTICAST(ntohl(ipa->sin.sin_addr.s_addr));
+}
+
+#endif /* IS_ENABLED(CONFIG_IPV6) */
+
+static inline bool netif_is_vxlan(const struct net_device *dev)
+{
+	return dev->rtnl_link_ops &&
+	       !strcmp(dev->rtnl_link_ops->kind, "vxlan");
+}
+
+struct switchdev_notifier_vxlan_fdb_info {
+	struct switchdev_notifier_info info; /* must be first */
+	union vxlan_addr remote_ip;
+	__be16 remote_port;
+	__be32 remote_vni;
+	u32 remote_ifindex;
+	u8 eth_addr[ETH_ALEN];
+	__be32 vni;
+	bool offloaded;
+};
+
+#if IS_ENABLED(CONFIG_VXLAN)
+int vxlan_fdb_find_uc(struct net_device *dev, const u8 *mac, __be32 vni,
+		      struct switchdev_notifier_vxlan_fdb_info *fdb_info);
+#else
+static inline int
+vxlan_fdb_find_uc(struct net_device *dev, const u8 *mac, __be32 vni,
+		  struct switchdev_notifier_vxlan_fdb_info *fdb_info)
+{
+	return -ENOENT;
+}
+#endif
+
 #endif